Bridging the Gap Between Target Networks and Functional Regularization

Authors:
  • APAlexandre Piche
    Alexandre Piche
  • VTValentin Thomas
    Valentin Thomas
  • JMJoseph Marino
    Joseph Marino
  • RPRafael Pardinas
    Rafael Pardinas
  • GMGian Maria Marconi
    Gian Maria Marconi
  • CPChristopher Pal
    Christopher Pal
  • MKMohammad Emtiyaz Khan
    Mohammad Emtiyaz Khan

Abstract
Bootstrapping is behind much of the successes of Deep Reinforcement Learning. However, learning the value function via bootstrapping often leads to unstable training due to fast-changing target values. Target Networks are employed to stabilize training by using an additional set of lagging parameters to estimate the target values. Despite the popularity of Target Networks, their effect on the optimization is still misunderstood. In this work, we show that they act as an implicit regularizer. This regularizer has disadvantages such as being inflexible and non convex. To overcome these issues, we propose an explicit Functional Regularization that is a convex regularizer in function space and can easily be tuned. We analyze the convergence of our method theoretically and empirically demonstrate that replacing Target Networks with the more theoretically grounded Functional Regularization approach leads to better sample efficiency and performance improvements.